{"id":"https://openalex.org/W2887171382","doi":"https://doi.org/10.1109/slt.2018.8639659","title":"Scaling and Bias Codes for Modeling Speaker-Adaptive DNN-Based Speech Synthesis Systems","display_name":"Scaling and Bias Codes for Modeling Speaker-Adaptive DNN-Based Speech Synthesis Systems","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2887171382","doi":"https://doi.org/10.1109/slt.2018.8639659","mag":"2887171382"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f76f48df-2edc-4daf-b3f5-886bc7cd8139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hieu-Thi Luong","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.6515,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76649553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8079873323440552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6186279058456421},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5583984851837158},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5311830043792725},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4812428951263428},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4723851680755615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3051937520503998},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.06428125500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079873323440552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6186279058456421},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5583984851837158},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5311830043792725},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4812428951263428},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4723851680755615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3051937520503998},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.06428125500679016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2018.8639659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f76f48df-2edc-4daf-b3f5-886bc7cd8139","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f76f48df-2edc-4daf-b3f5-886bc7cd8139","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luong, H-T & Yamagishi, J 2019, Scaling and Bias Codes for Modeling Speaker-Adaptive DNN-based Speech Synthesis Systems. in IEEE 2018 Workshop on spoken language technology (SLT 2018). Institute of Electrical and Electronics Engineers, Athens, Greece, pp. 610-617, 2018 IEEE Workshop on Spoken Language Technology (SLT), Athens, Greece, 18/12/18. https://doi.org/10.1109/SLT.2018.8639659","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f76f48df-2edc-4daf-b3f5-886bc7cd8139","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8639659","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f76f48df-2edc-4daf-b3f5-886bc7cd8139","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f76f48df-2edc-4daf-b3f5-886bc7cd8139","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luong, H-T & Yamagishi, J 2019, Scaling and Bias Codes for Modeling Speaker-Adaptive DNN-based Speech Synthesis Systems. in IEEE 2018 Workshop on spoken language technology (SLT 2018). Institute of Electrical and Electronics Engineers, Athens, Greece, pp. 610-617, 2018 IEEE Workshop on Spoken Language Technology (SLT), Athens, Greece, 18/12/18. https://doi.org/10.1109/SLT.2018.8639659","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1981706894","https://openalex.org/W2002342963","https://openalex.org/W2056738732","https://openalex.org/W2080400971","https://openalex.org/W2094147890","https://openalex.org/W2094721231","https://openalex.org/W2121981798","https://openalex.org/W2153914468","https://openalex.org/W2294543795","https://openalex.org/W2471520273","https://openalex.org/W2508162385","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2605320104","https://openalex.org/W2695252763","https://openalex.org/W2746498480","https://openalex.org/W2750322757","https://openalex.org/W2759925408","https://openalex.org/W2767767449","https://openalex.org/W2785364623","https://openalex.org/W2786149683","https://openalex.org/W2786868129","https://openalex.org/W2787685498","https://openalex.org/W2788357188","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2802968248","https://openalex.org/W2808706139","https://openalex.org/W2889064624","https://openalex.org/W2889329491","https://openalex.org/W2889374926","https://openalex.org/W2890606114","https://openalex.org/W2949382160","https://openalex.org/W2962691331","https://openalex.org/W2962739369","https://openalex.org/W2963192573","https://openalex.org/W2963381607","https://openalex.org/W2963411216","https://openalex.org/W2963432880","https://openalex.org/W2963912679","https://openalex.org/W2963927338","https://openalex.org/W2964169091","https://openalex.org/W2964243274","https://openalex.org/W4295731579","https://openalex.org/W4298174729","https://openalex.org/W6696912008","https://openalex.org/W6736204136","https://openalex.org/W6743548616","https://openalex.org/W6748140763","https://openalex.org/W6748233433","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6750489868","https://openalex.org/W6752888775"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W2490303674","https://openalex.org/W1533421371","https://openalex.org/W2609066826"],"abstract_inverted_index":{"Most":[0],"neural-network":[1,52],"based":[2,53,131],"speaker-adaptive":[3,54,88,101],"acoustic":[4],"models":[5],"for":[6,87],"speech":[7],"synthesis":[8],"can":[9,61,69,95,120],"be":[10,62,70],"categorized":[11],"into":[12],"either":[13],"layer-based":[14],"or":[15,37],"input-code":[16],"approaches.":[17],"Although":[18],"both":[19,107],"approaches":[20,60,108],"have":[21],"their":[22,111],"own":[23],"pros":[24],"and":[25,68,81,103],"cons,":[26],"most":[27],"existing":[28],"works":[29],"on":[30,34,132],"speaker":[31,125,129],"adaptation":[32,126,130],"focus":[33],"improving":[35],"one":[36],"the":[38,48,77,117,122,133],"other.":[39],"In":[40],"this":[41],"paper,":[42],"after":[43],"we":[44,56,75,94],"first":[45],"systematically":[46],"overview":[47],"common":[49],"principles":[50],"of":[51,79,106,124],"models,":[55],"show":[57,115],"that":[58,116],"these":[59,92],"represented":[63],"in":[64],"a":[65,97],"unified":[66],"framework":[67],"generalized":[71,85],"further.":[72],"More":[73],"specifically,":[74],"introduce":[76],"use":[78],"scaling":[80],"bias":[82],"codes":[83],"as":[84],"means":[86],"transformation.":[89],"By":[90],"utilizing":[91],"codes,":[93],"create":[96],"more":[98],"efficient":[99],"factorized":[100],"model":[102],"capture":[104],"advantages":[105],"while":[109],"reducing":[110],"disadvantages.":[112],"The":[113],"experiments":[114],"proposed":[118],"method":[119],"improve":[121],"performance":[123],"compared":[127],"with":[128],"conventional":[134],"input":[135],"code.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}